Search Results for author:
Found 32 papers, 7 papers with code
Dissecting Deep RL with High Update Ratios: Combatting Value Overestimation and Divergence
We show that deep reinforcement learning can maintain its ability to learn without resetting network parameters in settings where the number of gradient updates greatly exceeds the number of environment samples.
Improving Adversarial Transferability via Model Alignment
During the alignment process, the parameters of the source model are fine-tuned to minimize an alignment loss.
Maximum Entropy Model Correction in Reinforcement Learning
We propose and theoretically analyze an approach for planning with an approximate model in reinforcement learning that can reduce the adverse impact of model error.
Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods
In the context of deep learning, our experiments show that SGD-trained neural networks have smaller Lipschitz constants, explaining the better robustness to input perturbations than those trained with adaptive gradient methods.
Efficient and Accurate Optimal Transport with Mirror Descent and Conjugate Gradients
We design a novel algorithm for optimal transport by drawing from the entropic optimal transport, mirror descent and conjugate gradients literatures.
Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning
We consider the problem of learning models for risk-sensitive reinforcement learning.
Distributional Reinforcement Learning
reinforcement-learning
$λ$-models: Effective Decision-Aware Reinforcement Learning with Latent Models
The idea of decision-aware model learning, that models should be accurate where it matters for decision-making, has gained prominence in model-based reinforcement learning.
Operator Splitting Value Iteration
We introduce new planning and reinforcement learning algorithms for discounted MDPs that utilize an approximate model of the environment to accelerate the convergence of the value function.
Value Gradient weighted Model-Based Reinforcement Learning
However, they tend to be inferior in practice to commonly used maximum likelihood (MLE) based approaches.
Model-based Reinforcement Learning
reinforcement-learning
+1
Deep Reinforcement Learning for Online Control of Stochastic Partial Differential Equations
In many areas, such as the physical sciences, life sciences, and finance, control approaches are used to achieve a desired goal in complex dynamical systems governed by differential equations.
Learning Object-Oriented Dynamics for Planning from Text
The advancement of dynamics models enables model-based planning in complex environments.
The act of remembering: a study in partially observable reinforcement learning
Learning memoryless policies is efficient and optimal in fully observable environments.
Partially Observable Reinforcement Learning
reinforcement-learning
+1
Beyond Prioritized Replay: Sampling States in Model-Based RL via Simulated Priorities
The prioritized Experience Replay (ER) method has attracted great attention; however, there is little theoretical understanding of such prioritization strategy and why they help.
Understanding and Mitigating the Limitations of Prioritized Experience Replay
Prioritized Experience Replay (ER) has been empirically shown to improve sample efficiency across many domains and attracted great attention; however, there is little theoretical understanding of why such prioritized sampling helps and its limitations.
SOAR: Second-Order Adversarial Regularization
Adversarial training is a common approach to improving the robustness of deep neural networks against adversarial examples.
Policy-Aware Model Learning for Policy Gradient Methods
This is in contrast to conventional model learning approaches, such as those based on maximum likelihood estimate, that learn a predictive model of the environment without explicitly considering the interaction of the model and the planner.
Frequency-based Search-control in Dyna
This suggests a search-control strategy: we should use states from high frequency regions of the value function to query the model to acquire more samples.
An implicit function learning approach for parametric modal regression
We empirically demonstrate on several synthetic problems that our method (i) can learn multi-valued functions and produce the conditional modes, (ii) scales well to high-dimensional inputs, and (iii) can even be more effective for certain uni-modal problems, particularly for high-frequency functions.
Value Function in Frequency Domain and the Characteristic Value Iteration Algorithm
We call the new representation Characteristic Value Function (CVF), which can be interpreted as the frequency domain representation of the probability distribution of returns.
Hill Climbing on Value Estimates for Search-control in Dyna
In this work, we propose to generate such states by using the trajectory obtained from Hill Climbing (HC) the current estimate of the value function.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
Dimensionality Reduction for Representing the Knowledge of Probabilistic Models
Most deep learning models rely on expressive high-dimensional representations to achieve good performance on tasks such as classification.
Improving Skin Condition Classification with a Visual Symptom Checker Trained using Reinforcement Learning
Moreover, the increased accuracy is up to 10% compared to the approach that uses the visual information provided by CNN along with a conventional decision tree-based QA system.
Iterative Value-Aware Model Learning
This paper introduces a model-based reinforcement learning (MBRL) framework that incorporates the underlying decision problem in learning the transition model of the environment.
Improving Skin Condition Classification with a Question Answering Model
We present a skin condition classification methodology based on a sequential pipeline of a pre-trained Convolutional Neural Network (CNN) and a Question Answering (QA) model.
Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control
Recent work has shown that reinforcement learning (RL) is a promising approach to control dynamical systems described by partial differential equations (PDE).
Random Projection Filter Bank for Time Series Data
Different filters in RPFB extract different aspects of the time series, and together they provide a reasonably good summary of the time series.
Attentional Network for Visual Object Detection
We propose augmenting deep neural networks with an attention mechanism for the visual object detection task.
Classification-based Approximate Policy Iteration: Experiments and Extended Discussions
We introduce a general classification-based approximate policy iteration (CAPI) framework, which encompasses a large class of algorithms that can exploit regularities of both the value function and the policy space, depending on what is advantageous.
Learning from Limited Demonstrations
We achieve this by integrating LfD in an approximate policy iteration algorithm.
Bellman Error Based Feature Generation using Random Projections on Sparse Spaces
This paper addresses the problem of automatic generation of features for value function approximation in reinforcement learning.
Action-Gap Phenomenon in Reinforcement Learning
Many practitioners of reinforcement learning problems have observed that oftentimes the performance of the agent reaches very close to the optimal performance even though the estimated (action-)value function is still far from the optimal one.
Error Propagation for Approximate Policy and Value Iteration
We address the question of how the approximation error/Bellman residual at each iteration of the Approximate Policy/Value Iteration algorithms influences the quality of the resulted policy.
